DE102009025856A1 - Processing and visualization technology of medical data - Google Patents

Abstract

A data processing technique is provided. In one embodiment, a computer-implemented method includes access (282, 284) to patient image and non-image deviation scores (250, 270) obtained by corresponding comparisons of patient image data and non-image data (242, 262). derived with standardized image data and non-image data. The method may also include processing (286) the image and non-image deviation scores to generate a visual result (296) that respectively indicates differences between the patient image data and non-image data and the standardized image data and non-image data. Further, the method of displaying (288) the visual result creation items may also be disclosed.

Description

BACKGROUND

The The present invention relates primarily to medical diagnostics and in particular the diagnosis of medical conditions from patient deviation data.

A Type of medical condition or illness that is medical Community of interest are the neurodegenerative diseases (NDDs), such as Alzheimer's disease and Parkinson's disease. Alzheimer's disease affects currently tens of millions of people worldwide and makes one large part the dementia cases in patients out. Furthermore, there is currently no known cure. The economic and social costs associated with Alzheimer's disease are significant and increase over time.

However, NDDs may be demanding to treat and / or investigate because they are both difficult to detect at an early stage and are unlikely to be quantified in a standardized manner for comparison between different patient populations. In response to these difficulties, researchers have developed methods to detect statistical deviations from normal patient populations. An element for the detection of NDD is the development in terms of age and indicator substances of subdivided normal databases. A comparison with these standards can only in a standardized area, eg. The Talairach area or the Montreal Neurological Institute (MNI) area. The MNI defines a standard brain using a large series of magnetic resonance imaging (MRI) scans on normal controls. The Talairach area refers to a brain cut open and photographed in the Talairach and Tournoux atlases. In both the Talairach area and the MNI area, data must be mapped to the appropriate standard area using alignment techniques. Current methods that use a variant of the above process include indicators NeuroQ ^®, Statistical Parametric matching (SPM), 3D stereotactic surface projections (3D-SSP), etc.

As soon as a comparison is done becomes a statistical deviation of the anatomy representing Image displayed, which allows a viewer to make a diagnosis on the Base of the picture. The position of such a diagnosis is a very special job and typically gets high trained medical image experts. however can Even such experts only a subjective statement regarding the Severity of the disease. Because of this inherent subjectivity, the Diagnoses tend to be inconsistent and non-standardized. It may therefore be desirable its consistency and standardization of such diagnoses increase. It may also be desirable be extra Include data, including non-image data, by one holistic approach to the To provide patient diagnosis.

Summary

Certain within the scope of the original Aspects of the invention are described below shown. It should be understand that these aspects are merely presented to the reader to provide a brief summary of certain forms of the invention, and that these aspects are not for that are intended to limit the scope of the inven tion. Instead For example, the invention may include a variety of aspects, which will be discussed below not shown.

According to one embodiment contains a system a memory device with a plurality of stored therein Routines, and one for execution of the multiple routines stored in the storage device Processor. The multiple routines may include a routine that configured for it is, an access to a patient image deviation score perform, the difference between patient image data and for a population segment representative Display reference image data. Furthermore, the multiple routines include a routine for that is configured to access a patient non-image deviation score to perform that a difference between patient non-image data and for the population segment representative Display reference non-image data. In addition, the multiple routines further include routines configured to generate a report with visual representations of deviations of the Patient image and non-image data from the corresponding reference image and generate non-image data and effect output of the report.

In another embodiment, a computer-implemented method includes access to at least one patient image deviation score derived by comparing patient image data to standardized image data representative of a population of individuals. The method may also include access to at least one or more patient non-image deviation scores derived by comparing patient non-image data to standardized non-image data representative of a population of persons become. Furthermore, the method may include processing the image and non-image deviation scores to generate a visual result indicative of differences between the patient data and the standardized data, and may include displaying the visual result to determine the medical condition of a patient To enable patients.

According to one another embodiment A computer-implemented method involves access on a deviation score of a patient by comparison of patient image data from at least two different imaging modalities standardized image data is calculated. The procedure can also the processing of the image deviation evaluation to generate a visual result that is a graphic Contains representation the difference between the patient image data and the standardized Displays image data. Furthermore, the method may display the indication of visual result.

According to one more another embodiment A computer-implemented method involves access on patient non-image deviation evaluations by a Comparison of timeline patient non-image data with standardized non-image data is calculated. The procedure can also be the processing the patient non-image deviation scores for generating a visual result, which is a graphical representation contains which detects a difference between at least one subset of the timeline patient non-image data and indicates the standardized non-image data. Furthermore, can the method includes displaying the visual result.

According to one more another embodiment For example, an article of manufacture includes a computer readable medium with executables stored on it Instructions. The executable Instructions can Include instructions that are adapted to one To access patient image deviation score from a comparison derived from patient image data with reference image data. The executable Instructions can also include instructions that are adapted to one To access patient non-image deviation score from a Comparison of patient non-image data is derived with reference non-image data.

Further can the executable Instructions contain instructions that are adapted, at least based in part on the image and non-image deviation scores to create a visual result, and that makes a difference between the patient image data and the reference image data, and a difference between the patient non-image data and the reference non-image data display visual result.

Various Refinements of the aforementioned features can be found in With respect to various aspects of the present invention. Other features can also be included in these various aspects. These Refinements and additional Features can individually or in combination. For example, different ones hereafter with respect to one or more of the illustrated embodiments features discussed in any of those described above Aspects of the present invention alone or in any combination be involved. Again, the short summary presented above is only for that provided the reader with certain aspects and contexts of the present invention without limitation with respect to the claimed subject matter of the invention to familiarize.

DRAWINGS

These and other features, aspects and advantages of the present invention become better understood, if the following detailed description with reference to the attached drawings is read, in which same reference signs the same parts throughout denote the drawings, wherein:

1 FIG. 4 is a block diagram of an exemplary processor-based device or system according to one embodiment of the present invention; FIG.

2 Fig. 10 is a block diagram of an exemplary data acquisition and processing system according to one embodiment of the present invention;

3 Fig. 10 is a flowchart of an exemplary method for generating feature extraction image data according to an embodiment of the present invention;

4 Fig. 10 is a flowchart of an exemplary method for generating a cortex map from brain image data in accordance with an embodiment of the present invention;

5 Fig. 10 is a flowchart of an exemplary method for generating deviation maps according to an embodiment of the present invention;

6 an exemplary visual mapping of cortex thickness data on an enlarged brain surface according to an embodiment of the present invention;

7 Figure 12 is a block diagram illustrating a division of reference data into standardized databases according to an embodiment of the present invention;

8th Fig. 10 is a flow chart of an exemplary diagnostic method according to an embodiment of the present invention;

9 Fig. 10 is a flow chart of an exemplary method for generating and analyzing deviation data according to an embodiment of the present invention;

10 Fig. 10 is a flowchart of a method for diagnosing a patient based on a comparison of a patient deviation map with reference deviation maps according to an embodiment of the present invention;

11 Fig. 10 is a flowchart of an exemplary method for generating a composite deviation map illustrating both a structural and functional departure according to one embodiment of the present invention;

12 Fig. 10 is a flowchart of a method for generating image deviation scores for a patient according to one embodiment of the present invention;

13 Figure 3 is a flow chart of a method for generating non-image deviation scores for a patient according to an embodiment of the present invention;

14 FIG. 10 is a flowchart of an exemplary method for generating a visual representation of patient deviation data based on deviation scores in accordance with an embodiment of the present invention; FIG.

15 an exemplary visual representation of a variety of patient deviation data according to an embodiment of the present invention;

16 Fig. 10 is a flowchart of an exemplary visualization method according to an embodiment of the present invention;

17 Fig. 10 is a flowchart of another exemplary visualization method according to an embodiment of the present invention;

18 Figure 12 is an illustration of an automatic comparison workflow for determining a severity level according to an embodiment of the present invention;

19 Figure 3 is a flow chart of an exemplary method for calculating a combined disease severity score;

20 10 is a block diagram illustrating, in essence, a process of comparing patient data with standardized data for multiple disease types and severity levels in accordance with an embodiment of the present invention;

21 represent a plurality of representative reference deviation maps that may be included in a reference library or database of such deviation maps according to one embodiment of the present invention; and

22 represent additional representative reference deviation maps that may be included in a reference library or database of deviation maps according to one embodiment of the present invention.

DETAILED DESCRIPTION

A or more specific embodiments The invention will be described below. In an effort to create a concise description of these embodiments to deliver not all features of an actual Implementation will be described in the description. It should be Understand that in the development of any such actual Implementations as with any engineering or design project made numerous implementation-specific decisions Need to become, to the specific goals of the developer, such. B. match with systemic and business related restrictions which vary from one implementation to another can. Furthermore, probably It can be seen that such a development effort is complex and time consuming but still a routine company in terms of interpretation, Production and production for the normal person skilled in the art with the benefit of this disclosure.

When elements of various embodiments of the present invention are introduced, the articles "one, one, one,""the,the," and "said, said," mean that one or more of the elements may be present , The terms "having,""containing," and "having" are intended to include and have the meaning that additional elements other than the listed elements may be present. Furthermore, although the term "exemplary" is used herein in connection with particular examples of aspects or embodiments of the presently disclosed art, it will be appreciated that these examples are illustrative only and that the term "exemplary" is not used herein to refer to any Preference or necessity is used with respect to a disclosed aspect or embodiment. Furthermore, any use of the terms "top", "bottom", "above", "below" and other positional terms and variations of these terms is for convenience only, but does not require specific orientation of the described components.

In the drawings and first in 1 is an exemplary processor-based system 10 for use in conjunction with the present technique. In one embodiment, the exemplary processor-based system 10 a general purpose computer, such as A personal computer configured to run a variety of software, including software that implements all or part of the techniques disclosed herein, including the methods and functionality described by the present disclosure. Alternatively, in other embodiments, the processor-based system 10 consist, inter alia, of a mainframe computer, a distributed computer system, or an application-specific computer or workstation configured to use all or part of the present techniques based on specialized software and / or hardware provided as part of the system be to implement. Furthermore, the processor-based system 10 contain either only one processor or multiple processors to facilitate the implementation of the functionality disclosed herein.

In essence, the exemplary processor-based system includes 10 a microcontroller or microprocessor 12 , such as A central processing unit (CPU), which performs various routines and processing functions of the system 10 To run. For example, the microprocessor 12 execute various operating instructions configured to effect certain processes, as well as software routines stored in a computer-readable medium, such as a computer-readable medium. B. a memory 14 (eg a random access memory) (RAM) of a personal computer or one or more mass storage devices 16 (eg, an internal or external hard disk drive or a solid state storage device, CD-ROM, DVD, or other storage device) are stored or provided by the article of manufacture. In addition, the microprocessor processes 12 Data provided as input to various routines or software programs, such as: For example, data provided in conjunction with the present techniques in computer-based implementations.

Such data may be in the memory 14 or the mass storage device 16 be stored or provided by them. Alternatively, such data may be for the microprocessor 12 via one or more input devices 18 to be provided. As those skilled in the art will appreciate, the input devices may 18 manual input devices, such. As a keyboard, a mouse or the like. In addition, the input devices 18 a network device, such as A wired or wireless Ethernet card, a wireless network adapter, or any of various input ports or devices configured to communicate with other devices in any suitable communication network, such as a wireless network adapter. As a local network or the Internet to enable. About such a network device, the system 10 Exchange data and communicate with other networked electronic systems regardless of whether they are nearby or from the system 10 are located away. It will be appreciated that the network may include various components to facilitate communication, including switches, routers, servers or other computers, network adapters, communication cables, and so on.

From the microprocessor 12 generated results, such. For example, the results obtained by processing data in accordance with one or more stored routines may be stored in a memory device, may be subject to additional processing, or may be sent to an operator via one or more output devices, such as a printer. B. a display device 20 and / or a printer 22 , to be delivered. Further, based on the illustrated or printed output, an operator may request additional or alternative processing, or additional or alternative data, e.g. B. via the input device 18 deliver. As one of ordinary skill in the art realizes, communication between the various components of the processor-based system 10 typically achieved by means of a chipset and one or more buses or interconnects which are the components of the system 10 connect electrically. It should be noted that in certain embodiments of the present techniques, the exemplary process sor-based system 10 may be configured to allow patient diagnosis, as discussed in greater detail below.

An exemplary system 30 for collecting and processing data is in 2 according to an embodiment of the present invention. The system 30 includes a data processing system 32 , which is configured to provide versatile functionality. It should be noted that in one embodiment, the data processing system 32 a processor-based system, such. For example, the system 10 may include any suitable combination of hardware and / or software code, routines, modules or instructions adapted to perform the functionality discussed herein, including performing various steps of the methods otherwise described herein. It should be noted that such software routines may be embodied in an article of manufacture (eg, a compact disk, hard disk drive, flash memory, RAM, or the like) and configured for execution by a processor to facilitate execution of the functionality described herein cause.

The system 30 can also have one or more data acquisition systems 34 for collecting data from or relating to a patient 36 contain. The patient data may include only one or both of image data and non-image data, and may include any of static data, dynamic data, and timeline data. In various embodiments, the data acquisition systems 34 Patient monitoring devices, imaging systems of various modalities, computers, or any other suitable systems that are capable of providing data regarding the patient 36 to collect or receive. For example, the data acquisition system 34 an X-ray system, a computed tomography (CT) imaging system, a magnetic resonance (MR) imaging system, a positron emission tomography (PET) imaging system, a single photon emission computed tomography (SPECT) imaging system, among others , a digital tomosynthesis imaging system, an electroencephalography (EEG) system, an electrocardiographic (ECG or ECG) system, an electromyography (IMG) system, an electroimpedance tomography (EIT) system, an electronystagmography system (ENG) system, a system adapted for collecting nerve conduction data, or any combination of these systems.

Various components of the system 30 including the data processing system 32 and the data acquisition systems 34 can communicate with each other through a network 38 be connected, which allows communication between such components. The system 30 may also include one or more databases, such as: For example, the databases 40 and 42 for storing data, such as. As by the data acquisition systems 34 collected data and data generated by the data processing system 32 are used or generated, including both patient data and standardized reference data, as discussed in greater detail below. In addition, the data processing system 32 Data directly from the data acquisition systems 34 , from the databases 40 and 42 or in any other suitable way.

In some embodiments, it may be desirable to analyze one or more features of interest from image data to enable a patient to be diagnosed on one or more disease types or disease severity. As a result, an exemplary method 48 for generating image data for feature extraction in general 3 according to an embodiment of the present invention. image data 50 can be from different sources such. B. one or more data acquisition systems 34 , Databases 40 or 42 or the like can be obtained. Furthermore, such image data can also be applied to a specific patient, such as a patient. For example, the patient 36 or related to one or more reference persons of a population sample. The procedure 48 can also have different steps, such. B. the steps 52 . 54 . 56 . 58 and 60 for processing, alignment and extraction of features of interest.

In the presently illustrated embodiment, the method includes a step 52 for preprocessing the image data. Such preprocessing may involve a lot of sub-processes, such as subprocesses. As intensity correction, comparisons, filters, etc. include. In the steps 54 and 56 can provide additional anatomical markers in the image data 50 can be detected, and an image grid can be generated. Based on the anatomical markers and the image grid, the data can be viewed in one step 58 be subjected to an assignment. Subsequent to the assignment, the features of interest in the image data 50 in one step 60 be extracted. Although certain exemplary steps of the procedure 48 be described herein, it should be noted that the image data 50 orientation or feature extraction over fewer, different, or additional steps in accordance with the present technique.

In one embodiment, the image data includes 50 one or more images of a human brain that is a Talairach coordinate system can be assigned. In such an embodiment, the image data of the human brain, which may include an MRI image or any other image, may be normalized and resampled as an internal matrix of 256 x 256 x 128 for further processing. Further, in one embodiment, the anterior and posterior commissures (AC-PC) of the brain image and other anatomical landmarks may be identified to facilitate Talairach alignment. The brain images of the image data 50 can be elastic, such. Be aligned by warping on the Talairach coordinate system to allow for later display, analysis and diagnosis.

It should be noted that the particular features of interest in the image data may vary depending on a particular disease or condition of interest. For example, in diagnosing neurological conditions, it may be useful to extract certain features of the brain image data to enable diagnosis. Further, in some embodiments, it may be desirable to determine the thickness of the cerebral cortex of a patient or one or more reference persons. Accordingly, an exemplary method for determining the cortical thickness of a brain from patient image data or reference image data and for creating a cortical thickness map in 4 according to an embodiment of the present invention.

The procedure 64 can take a step 68 for segmenting brain tissue into image data 66 from other anatomical structures outside the brain, such as B. the skull included. Furthermore, in step 70 white matter of the brain and subcortical areas, such as. As ventricles are segmented by the gray matter of the cerebral cortex. In one embodiment, since the relative image intensities of the white matter of the brain and other soft tissues may be very close or superimposed, in one embodiment the segmented brain may be manually edited to remove unwanted residual tissue or to restore accidentally deleted cortical tissue generally one step 72 equivalent. Furthermore, a segmentation of white matter, surface adaptation and smoothing in the steps 74 and 76 be performed. In one step 78 For example, the meninges or pia surface (ie, the outer surface of the gray matter of the brain) can be detected. It should be noted that the pia surface generally contains numerous turns and furrows, but may be considered regionally smooth to facilitate processing. The pia surface can be detected in various ways, such as. By the use of a deformable model or displacement from the surface of the white matter. The thickness of the cerebral cortex (ie the cortex thickness) can be in one step 80 can be calculated, and a cortex thickness map, which visually represents the cortex thickness, can in one step 82 be generated.

In some embodiments can standardized reference cortex thickness maps calculated from image data that are used by other persons or groups of persons (eg normal persons, persons with diagnosed Alzheimer's disease (AD), persons with diagnosed Parkinson's disease (PD), persons with diagnosed frontotemporal dementia (FTD) and so on and in big ones Databases are stored, such. For example, those diagnosed by Alzheimer's Disease Neuroimaging Initiative (ADNI). Such standardized cards can used as reference image data relating to cortex measurements of patients be, and can according to any properties be grouped and standardized. For example, in an embodiment of such Data based on a demographic characteristic, such as The race, sex, or age of the persons, from which the data was collected. Such standardized Allow data the calculation of the average cortex thickness of normal patients and the thickness distribution over different functional areas of the brain, the memory, Movement, speech, language, listening, Seeing, feeling, emotion etc. concern. The cards of average cortex thicknesses can be the reference image data are generated and also dependent on Age, gender or race distributions are standardized or according to any other properties of interest. Although certain currently disclosed embodiments be described in terms of brain features, such. The cortical thickness, you will realize that the thicknesses are more general any features of interest, including those of image data applied from other anatomical areas outside the brain can be.

In some cases, it may be desirable to include anatomical deviation maps, such as G., Cortex thickness deviation maps that indicate differences between the anatomical area of a patient and an anatomical reference area. Thus, an exemplary process 88 for generating deviation maps of standardized reference data in 5 according to an embodiment of the present invention. In the presently illustrated embodiment, reference image data becomes 90 in one step 92 standardized. As mentioned above, reference image data can be collected from a population of people and according to one or more of several desired properties, such. Age, sex or race, grouped or standardized. Although the embodiment illustrated herein is described with respect to image data, it should be appreciated that reference non-image data and non-image data from patients may instead be used to generate the deviation maps discussed herein in full accordance with the present technique.

The procedure 88 can also take a step 94 a selection of a subset of the standardized reference image data based on a patient property include. For example, if a patient is a 65-year-old woman, a subset of the standardized reference image data grouped to include reference images relating to women between the ages of 60 and 70 may be more relevant for comparison purposes than a group of standardized ones Reference images composed of data collected by men between the ages of 20 and 30 years. Once a desired group of standardized image data is selected, the appropriate standardized image data 96 with the image data 100 of the patient in the step 98 be compared. In another embodiment, patient non-image data may instead also be compared to appropriate standardized non-image data as described above. In addition, the various data may be processed and standardized in any suitable manner to facilitate such comparisons.

On the basis of such a comparison, the difference between the patient image data 100 and the standardized image data 96 representing patient deviation map in step 102 be generated. For example, regarding cortex thickness, a patient cortex thickness map can be obtained by comparing the patient cortex map with a standardized cortex map based on a representative population of normal subjects. Thus, in one embodiment, the patient cortex thickness deviation map may substantially represent differences in the cortex thickness of the patient relative to normal individuals of similar age, sex, or race. The deviation maps described herein may be generated by any suitable technique. The deviation maps described herein may be generated by any suitable technique. In one embodiment, a deviation map is a visual representation in which each point on the map represents a z score substantially equal to the number of standard deviations (based on a population) in the difference between a patient value and the average (population) for corresponds to this point. Although such deviation maps may be calculated from image data, it should be noted that deviation maps may be generated using one or more of numerical data, text data, waveform data, image data, video data, or the like.

The various anatomical area maps described herein and deviation maps can visualized to allow further analysis or diagnosis. For example, you can any or all of the standardized cortex card, the Patient Cortex Thickness Maps, Patient Cortex Thickness Variance Maps, or standardized cortex thickness deviation maps (as below described) as surface matrices expressed be, and can on a three-dimensional (3D) brain surface, a pia surface or an enlarged brain surface shown or superimposed become.

Within the scope of a further example, such a representation possibility is in 6 according to an embodiment of the present invention. In particular, cortex thicknesses or deviations on an enlarged brain surface 108 as shown within a window 110 being represented. Different areas of the brain 108 can according to a scale 112 color coded to represent the cortex thicknesses or a deviation from the normal thickness to allow the user to understand the anatomical information presented.

In addition, reference data may be stored in standardized databases such as, for example, a generic database 7 illustrated exemplary method 118 can be classified and sorted according to an embodiment of the present invention. The procedure 118 can access to reference data 120 containing known population image data and the classification of such data in one step 122 include. For example, the reference data 120 be classified into different groups, such. Eg data 124 for normal patients; dates 126 for patients with a first condition, such. B. Alzheimer's disease (AD) are clinically diagnosed; dates 128 , for patients with a second condition, such. B. a frontotemporal dementia (FTD) are diagnosed; and dates 130 for patients with other conditions, such. Parkinson's disease (PD), Huntington's disease (HD), multiple infarct dementia (MID), diffuse cortical Lewy body disease (DLBD), normal pressure hydrocephalus, progressive supranuclear paralysis (PSP), or the like. Although certain brain disorders, brain image data and brain deviation maps are available for the purpose of the explanations Once again, it should be noted that the use of the present techniques with other non-neurological data and diseases is also conceivable. The data 124 . 126 . 128 and 130 can in appropriate databases 132 . 134 . 136 and 138 be saved. Such databases may be stored in one or more memory devices or in any other suitable medium.

An exemplary procedure 144 for diagnosing a patient based at least in part on the above data is in 8th according to an embodiment of the present invention. The procedure 144 can generate a patient map of a structural feature in one step 146 based on received patient data 148 include. In a related to brain disorders embodiment, the in step 146 generated patient card be a cortex card of the patient. In one step 150 becomes a normalized map of a feature on the basis of the data 124 generated for normal patients. For example, a standardized cortex map for normal patients can be generated in this step. Although the presently illustrated embodiment is discussed with reference to structural features maps, it is to be understood that maps of other features, such as those shown in FIGS. Functional or metabolic features may instead be used in full accordance with the presently disclosed technique.

In one step 152 For example, reference state maps (eg, mean maps or other reference maps) of the structural feature for each diagnosed state or disease may be based on the reference data 126 . 128 and 130 generated with respect to persons of a population with the diagnosis of such conditions. For example, in one embodiment, a representative average cortex map may be included for each brain disease of interest, such as the brain disorder of interest. B. AD, FTD, PD or the like can be calculated. Additional mean cards (or other reference cards) that correspond to different severity levels in a disease type can also be generated. Thus, multiple representative or average maps can be generated for each diagnosed state or disease type.

The procedure 144 can also take a step 154 a comparison of a patient's maps and normal maps, and a step 156 a comparison of the reference state and normal maps. In one embodiment, the method 144 one step 158 a comparison of one or more patient deviation maps (which results from the comparison of the step 154 can be generated) with one or more disease reference deviation maps (which are from the comparison of the step 156 can be generated). It should be appreciated that the cards discussed above and other cards and data described herein may be standardized into one or more general or similar formats to facilitate analysis and comparison. It will also be appreciated that the various cards described herein may be stored in one or more databases to facilitate subsequent data analysis. In addition, some or all of the above comparisons may be performed either automatically by a data processing system (eg, a system 32 ), by a treating person (eg a doctor) or any combination thereof, to perform an automatic or manual diagnosis of the patient in one step 160 to enable. Such a diagnosis may also be based on additional data, such as. B. clinical data 162 , Laboratory data, patient history, patient vital signs, results of various tests (eg, functional tests, cognitive tests, neurological tests or genetic tests), etc. In addition, in one step 164 of the procedure 144 a report 166 to a database 168 for storage or to a user in a human-readable format.

Numerous reference and patient deviation data and maps can be generated based on the patient and reference data and maps discussed above. For example, an exemplary method 172 for generating and analyzing such deviation data in 9 according to an embodiment of the present invention. The procedure 172 includes access to reference cortical thickness data for: Normal Patients without Diagnosed Brain Disease (Data 174 ), Patients with clinically diagnosed AD (data 176 ), Patients with diagnosed FTD (data 178 ) and patients with diagnosed PD (data 180 ). The procedure 172 may also have access to patient cortex data 182 include. It will be appreciated that in other embodiments, the method 172 reference cortical thickness data for other brain disorders which may be processed in a similar manner to those discussed in detail in the illustrated example. In fact, the present processing techniques can also be applied to other non-brain related disorders.

In one step 184 can the normal data 174 with all other data 176 . 178 . 180 and 182 compared to patient deviation data 186 , AD deviation data 188 , FTD deviation data 190 and PD deviation data 192 to produce which all deviations from the normal data 174 can represent. Such deviation data may include structural deviation maps, such as. Cortex thickness deviation maps representative of differences between patient data and disease type reference data on the one hand, and normal reference data on the other hand. Additionally, the deviation data may also include functional deviation maps that are functional rather than structural differences between the patient (or reference data indicative of reference disease types) and normal individuals. In some embodiments, structural deviation maps may include cortical thickness deviation maps, and functional deviation maps may include cerebral blood flow rate deviation maps or metabolic rate deviation maps.

In step 194 such deviation data can be analyzed. For example, in one embodiment, a patient cortex thickness deviation map may be compared to representative reference cortex thickness deviation maps for each of the above-mentioned brain disorders to facilitate diagnosis of the patient for one or more of such brain disorders. In one embodiment, such an analysis may provide pattern matching of patient cards and reference cards and confidence levels of such matching to a user. Finally, results can be 202 analysis to a memory or user.

A procedure 194 for analyzing the data discussed above and diagnosing a patient is described in US Pat 10 according to an embodiment of the present invention. In one step 208 For example, one or more patient deviation maps, which may include a structural deviation map (eg, a cortex thickness deviation map) or any other deviation map (eg, a functional deviation map), may be associated with one or more reference deviation maps, such as a deviation map. As described above, are compared. Obviously, the reference deviation maps may include deviation maps (eg, functional deviation maps or metabolic deviation maps or structural deviation maps) that are representative of one or more disease types as well as different degrees of severity of the one or more disease types.

On the basis of such comparisons, one or more patient disease types and / or disease severity levels may be determined in step 210 identified and in one step 212 be diagnosed. In some embodiments, such as. As a fully automated embodiment, the steps 210 and 212 be combined. However, in other embodiments, the identification and diagnosis may be performed as separate steps. For example, the data processing system 32 Identify various types of disease or severity and present the identified disease types or severity levels to a user for diagnosis. A report 214 may include an indication of the identified patient disease types or severities, the diagnosis, or both.

In some embodiments, it may be desirable to combine displays of functional deviations and structural deviations of a patient relative to reference data, and to output such deviations in a visual manner that enables efficient diagnosis of a patient by a treating individual. Consequently, an exemplary method 218 for the generation of a composite deviation map indicating both a structural and a functional deviation, in 11 according to an embodiment of the present invention. In the presently illustrated embodiment, the method includes 218 the steps 220 and 222 for access to structural or functional data for a patient. The patient's structural and functional data may include various image and non-image data relating to an anatomical region of the patient. In one embodiment, the anatomical region may include the patient's cerebral cortex. Additionally, the patient's structural and functional data may include image data obtained from different imaging modalities.

The structural and functional data of the patient can be compared with standardized structural or functional reference data in the steps 224 and 226 be compared. As noted above, the reference data may be related to any desired characteristic, such as the desired property. For example, but not limited to, age, gender or race may be standardized. Based on such comparisons, one or more structural deviation maps may be provided to the patient in one step 228 can be generated, and one or more functional deviation maps of the patient in one step 230 be generated. In one embodiment, the patient's structural deviation map may show a deviation of the cortex thickness of the patient from one or more specific locations of the patient's cerebral cortex relative to the expected thickness represented by the standardized reference data. In a further embodiment, the patient's structural deviation map can be determined by means of a comparison of MR image the patient and the standardized reference data are generated. Even in a neurological context, the functional deviation map of the patient may be a deviation of the patient brain function, such. A cerebral blood flow rate or metabolic rate, of standardized rates. It will be appreciated, however, that the deviation maps may be generated based on a wide array of image data and / or non-image data as discussed above.

It should again be noted that the patient's structural deviation map may substantially represent structural differences of an anatomical region of the patient relative to standardized reference data for a similar anatomical region. For example, in one embodiment, the patient's structural deviation map may include a cortex thickness deviation map for the patient relative to standardized cortex thickness data such as those described above. Again, the patient's functional deviation map may represent non-structural differences between an anatomical region of a patient and a corresponding anatomical region of standardized data. For example, in some embodiments, the patient's functional deviation map may indicate differences in metabolic activity or other functional activity between the patient and standardized reference data. In order to facilitate easy and efficient communication of such differences to a user, a composite patient deviation map that indicates both the functional and structural differences discussed above may be performed in one step 232 be generated.

The structural deviation map of the patient and the functional Deviation map of the patient can along with any additional ones Difference cards can be combined in any suitable way to generate the composite patient deviation map. For example, in an embodiment the individual patient deviation maps are superimposed to only one create a single composite patient deviation map the multiple deviations of the patient in terms of standardized Displays data. In a further embodiment, the individual functional and structural deviation maps of the Patients are combined by means of a picture merge process. In particular, in one embodiment the structural deviation map of the patient by comparison of patient image data and standardized image data generated from each of a first imaging modality be while the functional deviation map of the patient from image data (of both the Patients as well as standardized reference sources), by a different from the first imaging modality second imaging modality to be obtained. For example, by comparison identified from MR images Structure deviations with functional image obtained from PET image data Deviations are combined to a single composite Patient deviation map that is both functional and also indicates structural deviations. In a further embodiment can be based on the structural deviation map of the patient a first criterion (eg, cortex thickness from MRI images) with the patient's structural deviation map based on a second Criteria (eg medial temporal lobe atrophy from CT images) I can be combined. In yet another embodiment can be based on the functional deviation map of the patient a first criterion (eg FDG, a well-known PET indicator recording in PET images) with a functional deviation map of the patient the basis of a second criterion (eg the inclusion of PIB, a well-known indicator of beta-amyloid in PET images) be combined.

In addition, different Colors for displaying and contrasting structural differences and functional differences. For example can in one embodiment functional deviations essentially in a compound Patient deviation map displayed by the color red while structural Deviations essentially through the use of the color blue can be displayed. additionally can the size of such deviations represented by different shades of red or blue to allow a physician or other user to quickly make patient deviations and the sizes of such Determine deviations, as well as a diagnosis of the patient too facilitate. However, one will realize that additional or additional Colors also indicate different types of deviations and their relative sizes used can be.

The procedure 218 can also be the output of the compound deviation map of the patient in one step 234 include. In some embodiments, the output of the patient's composite deviation map may also include storing the composite deviation map of the patient in a storage device. In further embodiments, the output of the composite patient deviation map may also or instead include providing the composite map in a human-readable format, such as By displaying the patient's composite deviation map on a display or by printing out a physical copy of the patient's composite deviation map. Further, the presently illustrated embodiment is currently presented as a parallel process related to the generation of separate structural and functional deviation maps of the patient. It should be noted that although the present exemplary method is described for illustrative purposes as a parallel process, the steps of all of the methods described herein may be performed in any suitable manner, and are not limited to execution in any particular order or manner.

The extent of the deviation of patient data from standardized data may also be translated into one or more deviation scores which, in one embodiment, are generally represented in FIG 12 and 13 shown method can be generated. An exemplary procedure 240 from 2 can access patient image data 242 and reference image data 244 include. Such image data may be from any suitable source, such as. A database or an imaging system. In fact, the image data 242 and 244 Image data from a variety of modalities and collected from a wide range of sources included. The reference image data 244 can be standardized with respect to any desired property. For example, in one embodiment, the reference image data 244 essentially represent features of normal individuals with particular demographic characteristics (eg, patient-like characteristics). In one step 246 can the patient image data 242 and the reference image data 244 be compared to deviations from the patient image data 242 from the reference image data 244 to investigate. In one embodiment, such differences may substantially represent a deviation (eg, structural or functional differences) of the patient from normal persons.

The procedure 240 can also take a step 248 a calculation of one or more patient image deviation scores for differences between the patient image data 242 and the reference image data 244 include. Such bias evaluations may include an arrangement of functional and structural aberrations of the patient relative to the reference image data, including deviations in metabolic activity (eg, fluorodeoxyglucose (FTG) metabolism that may be observed in PET images) in the physical anatomy (eg, cortical thickness, which can be measured in MR images), and functional activity (eg, Pittsburgh Compound B (PIB) measure, which can be determined from PET images), just a few call, show. The patient image deviation scores can be calculated in several ways, such as: On the basis of a projection deviation, a single-pixel (2D) deviation, a single-voxel (3D) deviation, or any other suitable technique. The calculated patient image deviation ratings 250 can then be in a database 252 stored, issued to a user, or additional processing in one or more steps 254 be subjected.

According to 13 can be an exemplary process 260 for computing non-image deviation scores, access to patient non-image data 262 and reference non-image data 264 include. The non-image data may be retrieved from any suitable source, such as A database, a computer or a patient monitoring device. The non-image data 262 The patient may include any non-image information that is collected for the purpose of diagnosing the patient, such as: Clinical data, laboratory data, patient history, patient vital signs, and the like, and may also include the results of functional tests, cognitive tests, neurological tests, genetic tests, etc. The non-image data 264 may contain similar data that may be standardized based on one or more population (s) or sample property (s). Further, in one embodiment, the patient non-image data 262 and reference non-image data 264 only one or both of numerical data and enumeration data (each of which may be contiguous or discrete). The reference non-image data 264 may be data representing characteristics of normal individuals with desired demographic characteristics (eg, characteristics similar to those of the patient). In one step 266 can the non-image data 262 of the patient with the reference non-image data 264 compared to identify any differences between the data. In one embodiment, such differences may substantially represent a deviation (eg, structural or functional differences) of the patient from normal subjects.

In addition, the process can 260 one step 268 for calculating one or more non-image deviation scores of the patient for differences between non-image data 262 of the patient and reference non-image data 264 include. It should be noted that various techniques are used to calculate the patient's non-imaging deviation scores including a z-score deviation or distributional analysis. Of course, it will be appreciated that other calculation techniques may or may not be used in other embodiments as well. The calculated non-image deviation ratings 270 the patient can in a database 272 stored, issued to a user or additional processing in one or more further steps 274 be subjected.

An exemplary procedure 280 for accessing patient deviation scores and for generating one or more visual representations to facilitate patient diagnosis is generally described in U.S. Pat 14 provided. The procedure 280 in one embodiment, includes access to one or more image deviation scores of the patient and one or more non-image deviation scores of the patient in the steps 282 respectively. 284 , These deviation evaluations can be done in one step 286 to produce a visual representation of the differences represented by the patient deviation scores. In one embodiment, the patient deviation scores may be derived from dynamic data (eg, video) or timeline data (eg, data acquired at discrete times over a predetermined duration) and a plurality of visuals representing the deviations at different times Representations can in step 286 be generated. The one or more visual representations may then be in one step 288 be issued to a diagnosis of the patient in one step 290 to enable. For deviations derived from dynamic data or timeline data, multiple visual representations can be output simultaneously or sequentially.

In some embodiments, the visual representation essentially includes a combination and visualization of the multiple differences represented by the bias scores, and thus provides a holistic view of patient deviations relative to standardized data. By way of example, an exemplary visual representation is provided 296 in 15 according to an embodiment of the present invention. It should be understood, however, that the presently illustrated embodiment is provided for purposes of illustration only, and that other visuals may take various forms.

In the presently illustrated embodiment, the visual representation includes 296 an area 298 for visualizing non-image deviation data maps of a patient, an area 300 for visualizing image data deviation maps of a patient or other image data, and a control field 302 , In various embodiments, numerous display techniques may be used to make the visualized deviation maps or other results more intuitive to a user and to more clearly convey the extent of deviation (eg, abnormality) in the results of the specific patient being examined. Such display techniques, as illustrated in the presently illustrated embodiment, may be a color mapping of image pixels or voxels and a color coding of individual cells in a table, the color coded cells each corresponding to a particular clinical test result and the color of the cells to the magnitude of the patient outcome variance compared to standardized data. Additional display techniques may also include temperature displays, spider web graphics, scales, font changes, annotations, or the like.

The exemplary visual representation 296 contains several cells 304 of which at least some non-image deviation maps of a patient are associated with corresponding clinical test results and are color-coded to give a visual indication of the extent of patient deviation from reference data for each test. For example, the cell 306 be assigned to a functional test, and be shaded in a color that is substantially the magnitude of the deviation of the result of the functional test for the patient compared to standardized results for the functional test. Likewise, cells can 308 and 310 be associated with a cognitive test or a blood sugar test and may be filled with special colors to indicate the size of the deviations of the patient results for such tests of standardized result data. Although the present illustration indicates discrete shades of color for the various cells, it will be appreciated that a contiguous color range may be used instead, and that any one or more desired colors may be used to efficiently communicate the extent of deviation of various clinical tests to a user , In addition, it should be noted that in the cells 304 can be based on any patient test having numerical or enumerated results that can be compared to standardized data and that such maps are not limited to those explicitly discussed herein.

Various image data can be in one area 300 the exemplary visual representation 296 are displayed. In the present dargestell th embodiment, several structural deviation maps 314 of the patient and functional deviation maps 316 of the patient in the upper and lower sections of the area, respectively 300 shown. These deviation maps of the patient may include various staining or shading to indicate a deviation of an anatomical region of a patient from standardized data. For example, the areas 318 . 320 and 322 in the structural deviation maps 314 In general, the patient's brain may correspond to sections of the patient's brain which show no or only a slight deviation from the standardized data, sections which show a moderate deviation and sections which each show a significant deviation. Embodiments relating to the human brain may include such structural deviation maps 314 a patient's cortex thickness deviation maps of the patient, which may be generated from MR image data. It should be noted, however, that the techniques disclosed herein are not limited to cortex thickness deviation data or brain images. Instead, the techniques disclosed herein are intended to enable quantification, visualization and diagnosis of a wide range of diseases and conditions.

The functional deviation maps 316 A patient may also include differently colored areas to represent the magnitude of the deviation of that area for the patient relative to standardized data. The functional deviation maps 316 A patient may, among other things, include data of a cerebral blood flow deviation or metabolic rate deviation of a patient from the standardized data, and in one embodiment, may be generated from PET image data. In these cards 316 can areas 328 none or only a small deviation from standardized data while ranges 330 and 332 show less or greater patient deviations from the standardized data. The use of three different presentation areas in the structural deviation maps 314 and functional deviation maps 316 a patient is used for simplicity and explanation purposes. It should be appreciated that other colors or shades may be used instead of or in addition to those illustrated herein, and such staining or shading may be produced in a continuous range or in discrete values.

The control panel 302 may allow presentation of more data to a user and user control of certain visualization processes. For example, in the presently illustrated embodiment, patient information may be in one area 340 can be represented, population information and selection control can be in one area 342 and various system parameters, test data or other information can be supplied in one area 344 to be delivered. In one embodiment, the population range 342 allow a user to select a particular set of standardized data from a library of standardized data sets based on a desired property. For example, a user may enter one or more of a desired age range, gender, or race, and the system may then display visual representations of patient deviations from the selected standardized record. In other words, in such an embodiment, the user may select demographics of the population segment of the standardized data with which the patient is being compared for purposes of visualization bias. Accordingly, in one embodiment, the user may select to visualize patient results as a measure of a deviation from a particular standardized demographically customized patient record.

Although the exemplary visual representation 296 Also, deviations from non-image data (eg, clinical tests, laboratory tests, etc.), other visual representations with different data, or only subset of the deviation data visualized above may be generated in other embodiments as well become. For example, in certain embodiments, the generated visual representation may include only deviation representations relative to other image data or non-image data rather than both.

For example, a visualization method 360 in 16 according to an embodiment of the present invention. The procedure 360 can take a step 362 access to patient image deviation scores for multiple imaging modalities, such as CT, MR, PET, SPECT, digital tomosynthesis or the like. The patient image deviation scores may be calculated by comparing patient image data with standardized reference data pertaining to a population of persons as generally described above. Further, in various embodiments, the patient image deviation scores may include a comparison of a patient's static image data or a dynamic image data (eg, video) of a patient acquired in only one imaging system or a patient's timeline image data collected over multiple imaging sessions were captured, with reference image data of a similar or under different types (eg static, dynamic or longitudinal). The patient image deviation scores accessed could be in one step 364 to generate a visual representation of a patient's deviation with respect to a visual representation of the patient's deviation with respect to the standardized image data as generally discussed above. The generated visual representation can be in one step 366 be issued to a diagnosis of the patient in one step 368 to enable.

An additional exemplary visualization process 370 is generally in 17 shown. The procedure 370 can access patient non-image deviation scores for dynamic data or timeline data in one step 372 include. Dynamic non-image data may include a substantially continuous series of clinical test results over a predetermined period of time, while non-image timeline data may include test results (or groups of test results) that may be displayed in a staggered manner (e.g., at 3-month intervals ) across multiple data collection sessions. As generally stated above, the patient non-image deviation scores for such data may be calculated based on a comparison of patient non-image data with standardized non-image data. In some embodiments, non-image data from patients on which the deviation scores are based may include non-image data from different modalities (eg, cognitive data, neurological data, and the like). The non-image deviation evaluations of patients can be done in one step 374 are processed to produce one or more visual results indicative of a deviation of the patient non-image data from the standardized non-image data. For example, in one embodiment, multiple visual results may be generated based on a comparison of a sequence of timeline patient non-image data with standardized non-image data. The visual representations can then be in one step 376 be issued to a diagnosis of the patient in one step 378 to enable. Multiple generated visual representations can be output simultaneously or sequentially.

18 is an exemplary representation of an automatic comparison workflow 400 , which generally represents the automatic generation of a disease severity index for various anatomical features of interest. The automatic comparison workflow 400 may include a number of anatomical features, such as. Structural or functional features of a brain, heart or the like. To illustrate the possibility of such a variety of anatomical features in a comparison, the automatic comparison workflow is 400 as having a first feature "A" 402 containing a second anatomical feature "B" 404 , a third anatomical feature "C" 406 , an "N-th" anatomical feature "N" 408 etc. shown containing. The automatic workflow comparison of 18 Figure 4 represents a specific implementation of the more generalized matching and presentation techniques described in US Patent Application Publication No. 2007 / 0078873A1, published April 5, 2007, entitled "COMPUTER ASSISTED DOMAIN SPECIFIC ENTITY MAPPING METHOD AND SYSTEM", which is incorporated herein by reference Entity is included are described. For example, in this specific implementation, the various anatomical features represent 402 . 404 . 406 . 408 different axes, while the disease severity deviation maps 410 . 412 . 414 . 416 which will be discussed below, represent different labels associated with each axis, etc.

For each anatomical feature, a number of deviation maps are provided with changes in the extent or severity of a disease or condition. For example, for the anatomical feature "A" 402 a number of reference deviation maps 410 with changes in the extent of a disease or condition associated with the anatomical feature "A". Similar sets of reference deviation maps 412 . 414 and 416 are provided which represent the deviations in the extent of disease or condition for each of the remaining corresponding anatomical features to the Nth feature. As those skilled in the art will recognize, each of these disease severity reference bias maps will be within the appropriate map sets 410 . 412 . 414 . 416 for the corresponding anatomical feature 402 . 404 . 406 and 408 and in the case of image data (rather than non-image data), reference deviation maps may also be categorized by an indicator or indicators (if one is used) and by the imaging technology used. For example, reference deviation maps within the corresponding deviation map sets 410 . 412 . 414 . 416 using magnetic resonance (MR) imaging, positron emission tomography (PET), computed tomography (CT), single photon emission computed tomography (SPECT), ultrasound, optical imaging or other conventional imaging techniques, and by using appropriate indicators under appropriate circumstances be generated. As discussed above, the reference deviation maps may also or instead of non-image data including clinical data be witnesses.

For each anatomical feature, the disease severity reference deviation maps are 410 . 412 . 414 . 416 the anatomical features as shown by the arrow 418 Depending on the severity of the disease or condition or otherwise assigned to a severity of the disease or condition. For example, for the anatomical feature "A" 402 the disease severity reference deviation maps 410 be arranged in an increasing order from the smallest extent or degree of disease or condition to the highest degree or degree of disease or condition.

In the illustrated embodiment, eight reference deviation maps are in each of the disease severity deviation map groups 410 . 412 . 414 . 416 as different disease severity levels associated with each anatomical feature 402 . 404 . 406 . 408 represented representatively. However, as those skilled in the art will appreciate, the number of reference deviation maps in the sets of these disease severity deviation maps is 410 . 412 . 414 . 416 arbitrary and can be increased or decreased depending on the implementation and the properties of the examiner. For example, in exemplary embodiments in which the comparison process is automated, the number of reference maps in each of the groups of disease severity maps may be 410 . 412 . 414 . 416 more than eight cards such. Ten, twenty, one hundred, etc. Further, although only a single disease severity reference deviation map is currently represented as any ordered severity level for each anatomical feature, each severity level for each anatomical feature may in fact have one or more disease severity reference deviation maps provided for comparison. For example, in exemplary implementations in which the comparison process is automated, any severity or severity index for an anatomical feature 402 . 404 . 406 . 408 represented by more than one disease severity reference deviation map.

Various patient deviation maps 420 may then relate to corresponding disease severity reference bias maps 410 . 412 . 414 . 416 be evaluated to a degree of disease or condition in the patient deviation maps 420 compared to the corresponding disease severity reference deviation maps. Each patient deviation card 420 for an anatomical feature can be generated by comparing acquired patient data with normative standardized anatomical data for the corresponding anatomical feature. As those skilled in the art will recognize, the patient deviation maps may be 420 from images using one or more suitable indicators (eg, when it is necessary to acquire desired functional information), derived from images captured by other techniques, or non-image data as described above. Therefore, in an exemplary embodiment, the patient-deviation maps based on image data 420 not just with a set of disease severity reference deviation maps 410 . 412 . 414 . 416 compared the same anatomical feature 402 . 404 . 406 . 408 but also with those reference maps in the set of disease severity reference deviation maps 410 . 412 . 414 . 416 which are generated from image data acquired using the same indicator (s), if any, and using the same or a similar imaging technology. In an exemplary embodiment, the comparison between the one or more maps of patient deviation maps becomes 420 and the corresponding set of disease severity reference deviation maps 410 . 412 . 414 . 416 automatically executed, such as Example by pattern matching or other comparable comparison techniques and routines.

For example, in one implementation, patient deviation maps 420 derived from the anatomical feature "A" 402 corresponding image data is automatically generated with the corresponding set of ordered disease severity reference deviation maps 410 which were generated from data generated using the same indicator (s) when an indicator was used, and using the same imaging modality as e.g. B. MR or PET were generated. As those skilled in the art will recognize, patient deviation maps may 420 and the corresponding disease severity reference deviation maps 410 . 412 . 414 . 416 with which they are compared, depending on patient-specific factors (such as a patient's history, patient symptoms, etc.) as well as clinical factors (such as the standard procedure of the treating physician or institution, previous diagnoses, years of experience, etc .) vary.

In the example presently illustrated, each comparison generates a severity index 422 that determines the extent of the disease in the corresponding patient deviation map 420 as determined by comparison with the anatomical feature-specific disease severity reference deviation maps 410 . 412 . 414 . 416 expresses or represents. As one skilled in the art will recognize, in the those embodiments in which the comparison is automatically performed, the severity index 422 also be generated automatically. In such embodiments, a viewer or evaluator may simply have a severity index 422 for any anatomical feature of interest or for what patient deviation maps 420 produced or processed.

In some embodiments, a summarized severity rating 424 the patient's disease from the indices of gravity 422 using statistical analysis 426 , such as A rule-based summarization method or technique. In an exemplary embodiment, the summarized severity score 424 automatically generated, such. By automatic implementation of the analysis 426 using appropriate routines or computer-implemented codes. In such embodiments, an observer or evaluator may simply be provided with a total or aggregate severity score for the patient.

In addition to calculating disease severity ratings or indexes for a patient with respect to a single disease type, the presently disclosed data processing system may also calculate a combined disease severity score based on a plurality of different disease types and severity levels. For example, an exemplary method 430 to determine a combined disease severity score for a patient based on multiple disease types and severity grades in 19 according to an embodiment of the present invention. The procedure 430 can take a step 432 accessing reference deviation data (such as reference deviation maps or other data) for multiple disease types. Such reference deviation maps may be standardized according to a demographic (or other) characteristic. In addition, the step 432 also include access to reference deviation maps or multiple severity data for one or more of the disease types. In one embodiment, the reference deviation data may include functional or structural deviation maps indicating differences between normal individuals and individuals with diagnosed specific disease types or with diagnosed severities of the different disease types. Disease severity ratings may include subsets of the reference deviation data, such as The different reference deviation data associated with different degrees of severity, as generally discussed above. On these individual disease severity assessments can also in one step 434 be accessed.

The procedure 430 may also include a selection of disease severity levels of the patient in one step 435 include. The choice of disease severity of the patient can be made in a variety of ways. In one embodiment, a user may compare a patient deviation map to a library or database of known deviation maps indicating a functional or structural bias associated with various disease types and / or severities. An exemplary visual reference library 484 known standardized deviation maps that correspond to normal patients and patients with diagnosed different types of disease is generally in the 21 and 22 and will be discussed with reference to this. In such an embodiment, the user may compare a patient deviation map with those reference deviation maps that are in the library 484 are included to diagnose the patient as having one or both of a specific disease type and severity. In one embodiment, to facilitate such manual analysis and comparison, one or more of the reference deviation maps or patient deviation maps may be represented by a computer system, and a user may select (via a user interface) a selection of specific severities for each type of disease corresponding to the patient deviation map specify the reference reference deviation map.

In a further embodiment, a calculation system, such. B. the data processing system 34 be programmed to automatically compare the patient deviation map with the reference deviation maps in the library of reference deviation maps and automatically select the best matches. Alternatively, various disease scores may be calculated based on given disease and severity levels and compared to a patient disease score to automatically determine and select the closest match. In yet another embodiment, a computing system may employ an algorithm to select a subset of the reference deviation maps from which a user makes a final selection.

Subsequent to the selection of patient severity grades for multiple disease types, a combined disease severity score may be automatically determined in step 438 be calculated. Finally, a report including or based on the combined disease severe evaluation in one step 440 be issued. As generally stated above, the output of the report, as well as other reports and data described herein, may include outputting the report to a memory, outputting the report to a user, or outputting the report to various software routines for further processing.

The method described above 430 can be used in conjunction with a variety of anatomical areas and disease types including, but not limited to, brain disorders. An exemplary process for evaluating brain disorders may be better with reference to the block diagram 450 to be understood, which in 20 according to an embodiment of the present invention is shown. Patient image data 454 and non-image data 456 can be from a patient 452 to be collected. As noted previously, such patient image data may include images obtained by any of various imaging modalities and may include patient cortex thickness maps, patient cortex thickness deviation maps, or any other desired image data. As also discussed above, the non-image data 456 From patients numerous number data types and information, such. B. Results of clinical tests and laboratory tests, family history, genetic history, etc. included. Based on the patient image data 454 can be determined that the patient 452 has a vascular disease, as is common in the block 458 is shown. Such a determination or diagnosis may be in a report 460 be issued. The patient image data 454 and the non-image data 456 The patient can also be used to determine if the patient is 452 has a neurodegenerative disease, as is common in the block 462 is shown.

The block 464 Essentially represents a workflow for determining patient severity levels for multiple brain diseases or disease types 466 , Several separate reference deviation maps 468 may be associated with any type of disease, and all of the several may represent substantially different degrees of severity of their respective disease type. Further, each reference deviation map may be associated with a disease severity score (eg, the S1 ... SN series for each disease type). For example, in one embodiment, the lowest disease severity score (ie, S1) reference deviation map representing the lowest severity of a particular disease may be associated with this disease type, while other reference aberration maps indicating an increase of different degrees of this disease type may be associated with increasing disease severity ratings (ie, S2, S3, ... SN) can. One or both of the patient image data 454 and the non-image data 456 of the patient can be compared with the sequence of reference deviation maps for disease type A (block 470 ) to a patient's disease severity 472 for the disease type A to determine. The individual disease severity score of patient X _A for disease type A may be the same as the disease severity score associated with the disease type A reference deviation map closest to the patient data with which it is compared. Alternatively, if the patient data suggests that the patient disease severity falls somewhere between two of the disease type A reference deviation maps, the individual patient disease severity score X _A may be calculated from the two disease severity scores associated with the individual reference deviation maps closest to the patient data. The individual severity scores for other disease types may be calculated in a similar fashion based on their own associated reference deviation maps.

Once the disease severity ratings 472 For the individual patient, for each disease type, such individual ratings may be used to calculate a combined disease severity score of the patient, as generally discussed in Block 474 is shown. The combined disease severity score of the patient may be calculated by adding the disease severity ratings of the individual patient, averaging the patient severity scores of the individual patient (which may be weighted as desired), or in any other suitable manner. Further, the patient's combined disease severity score may also indicate the relative contribution for each disease type to a patient's condition. For example, the patient's combined disease severity score may indicate that Alzheimer's disease is the major contributor to patient dementia or some other condition. In another embodiment, the patient's combined disease severity score may indicate the relative contribution of each of a plurality of disease types to a patient's condition. For example, the patient's combined disease severity score may indicate the relative contribution of various brain disorders to the patient's dementia (eg, 40% AD, 30% FTD, 30% others). A report 476 based on or indicating the patient's combined disease severity score may be output to a user or to a memory.

As mentioned above, reference images and deviation maps are of an exemplary visual reference library 484 in the 21 and 22 according to an embodiment of the present invention. It should be noted that the representations shown herein are for illustrative purposes only, and that an actual implementation of a visual reference library may contain other or additional images. In fact, various embodiments of a visual reference library 484 a significantly larger number of images such. 10, 100 or even larger numbers of reference images or maps, which may be standardized in various embodiments as discussed above. One will further recognize that images in the visual reference library 484 can be obtained by means of one or any number of imaging modalities, and original images, deviation maps such. For example, those discussed above or any other suitable reference images. In the presently illustrated embodiment, the reference images essentially represent metabolic rate deviations between normal individuals and individuals with various brain disease diagnoses. However, in other embodiments, other deviation maps, such as, e.g. Cortex thickness deviation maps, cerebral blood flow rate deviation maps or even deviation maps for non-brain anatomies in the visual reference library 484 be included.

In the presently illustrated embodiment, the visual reference library is 484 as a set of reference pictures 486 for normal people, and reference deviation maps 488 and 490 containing patients clinically diagnosed with mild or severe forms of, for example, Alzheimer's disease (AD). The visual reference library 484 can be deviation maps 492 included patients with a diagnosis of diffuse cortical Lewy body disease (DLBD) and deviation maps 494 , which correspond to patients with the clinical diagnosis of anterior temporal lobe dementia (FTD). The visual reference library 484 can also additionally deviation cards, such. B. progressive supranuclear paralysis (PSP) maps assigned 496 Multiple Infarct Dementia (MID) maps assigned 498 , and normal pressure hydrocephalus (NPH) maps assigned 500 contain.

Technical Effects of one or more embodiments of the present invention Invention can the diagnosis of different patient disease types and severity and the provision of decision support tools for one Include user diagnosis of patients. In one embodiment technical implications include the visualization of clinical Image and non-image information of a patient together in one holistic, intuitive and even way, which is an efficient Diagnosis by a viewer allows. In a further embodiment technical implications include the calculation of patient cortex deviation maps and reference cortex deviation maps of known brain diseases that Calculation of additional Patient and reference deviation maps, and the combination of such Maps with other clinical tests to get a quantitative rating and to enable diagnosis of brain diseases.

Even though only certain features of the invention are illustrated and described herein Many modifications will become apparent to those skilled in the art and changes possible appear. It should be It is therefore to be understood that the appended claims all such modifications and changes as far as they are in the actual idea of the invention fall of the invention.

A data processing technique is provided. In one embodiment, a computer-implemented method includes access 282 . 284 on patient image and non-image deviation evaluations 250 . 270 by comparing comparisons of patient image data and non-image data 242 . 262 derived with standardized image data and non-image data. The procedure can also be the processing 286 the image and non-image deviation scores for generating a visual result 296 each indicating differences between the patient image data and non-image data and the standardized image data and non-image data. Furthermore, the method can display 288 of the visual result. Additional methods, systems and articles of manufacture are also disclosed.

10

Processor-based system

12

microprocessor

14

Storage

16

Mass storage device

18

input device

20

display device

22

printer

24

26

28

30

data collection and processing system

32

Data processing system

34

Data Acquisition System

36

patient

38

network

40

Database

42

Database

44

46

48

method

50

image data

52

preprocessing of data

54

detect anatomical markings

56

Produce a picture grid

58

alignment

60

extraction of features of interest

62

64

method

66

image data

68

brain segmentation

70

subcortical segmentation

72

edit of segmentation results

74

segmentation the white one substance

76

surface fitting and smoothing the white one substance

78

detect the pia surface

80

To calculate the thickness of the cerebral cortex

82

Produce a cortex card

84

86

88

method

90

Reference image data

92

Standardize of reference image data

94

Select one Subset of standardized image data

96

Suitable standardized image data

98

to compare of image data

100

Patient image data

102

Patient deviation map

104

106

108

Enlarged brain surface

110

window

112

scale

114

116

118

method

120

reference data

122

Classify of data

124

dates for normal patients

126

dates for patients with diagnosis of the first condition

128

dates for patients with diagnosis of the second state

130

dates for patients with diagnosis of other conditions

132

Normal database

134

Database

136

Database

138

Database

140

142

144

method

146

Produce a patient card

148

patient information

150

Produce a normal card

152

Produce a state map

154

to compare of patient and normal maps

156

to compare of normal and state cards

158

to compare of patient and reference deviation maps

160

Diagnose of the patient

162

clinical dates

164

Output a report

166

report

168

Database

170

user

172

method

174

Reference Cortex Thick Data - Normal

176

Reference Cortex Thick Data - AD

178

Reference Cortex Thick Data - FTD

180

Reference Cortex Thick Data - PD

182

Patient cortex thickness data

184

to compare normal data with other data

186

Patient deviation data

188

AD-deviation data

190

FTD deviation data

192

PD-deviation data

194

Analyze of data

196

clinical reference data

198

clinical patient information

200

Other dates

202

Results

204

206

208

to compare a patient deviation map with reference deviation maps

210

Identify one or more patient disease types and / or disease severity

212

Diagnose of the patient

214

report

216

218

method

220

Access on structural patient data

222

Access on functional patient data

224

to compare of patient data with structural reference data

226

to compare of patient data with functional reference data

228

Produce a structural deviation map of the patient

230

Produce a functional deviation map of the patient

232

Produce a composite deviation map of the patient

234

Output a composite deviation map of the patient

236

240

method

242

Patient image data

244

Reference image data

246

to compare patient and reference image data

248

To calculate of patient image deviation ratings

250

Patient image deviation scores

252

Database

254

additional processing

256

258

260

method

262

Patient non-image data

264

Reference non-image data

266

to compare patient and reference non-image data

268

To calculate patient non-image deviation ratings

270

Patient non-image deviation scores

272

Database

274

additional processing

276

278

280

method

282

Access on patient image deviation ratings

284

Access on patient non-image deviation ratings

286

To process from deviation evaluations to visual representations of deviations to create

288

Output a visual representation

290

Diagnose of the patient

292

294

296

visual presentation

298

Area

300

Area

302

control field

304

cell

306

cell

308

cell

310

cell

312

314

structural Deviation maps of the patient

316

functional Deviation maps of the patient

318

Area

320

Area

322

Area

324

326

328

Area

330

Area

332

Area

334

336

338

340

Area

342

Area

344

Area

346

348

350

354

356

358

360

method

362

Access on patient image deviation scores for multiple modalities

364

To process of deviation evaluations to produce a visual representation of deviation

366

output the visual representation

368

Diagnose of the patient

370

method

372

Access on non-image deviation evaluations of the patient for dynamic Data or timeline data

374

To process from deviation evaluations to a visual representation of deviations to create

376

Output one or more visual representations

378

Diagnose of the patient

380

382

384

386

388

390

392

394

394

396

398

400

work routine the automatic comparison

402

anatomical feature

404

anatomical feature

406

anatomical feature

408

anatomical feature

410

Reference deviation map for anatomical feature

412

Reference deviation map for anatomical feature

414

Reference deviation map for anatomical feature

416

Reference deviation map for anatomical feature

418

arrow

420

Patient deviation maps

422

severity index

424

summarized Disease severity rating of the patient

426

statistical analysis

428

430

method

432

Access on reference deviation data

434

Access on individual disease severity ratings

436

Select from Disease severity of the patient

438

To calculate a combined disease severity rating

440

Expense report

442

444

446

448

450

block diagram

452

patient

454

Patient image data

456

Patient non-image data

458

vascular disease

460

report

462

neurodegenerative illness

464

workflow to determine patient disease severity

466

types of diseases

468

Reference deviation maps

470

to compare with patient data

472

individual Disease severity rating of the patient

474

combined Disease severity rating of the patient

476

report

478

480

482

484

visual reference library

486

Normal reference images

488

Mild AD deviation maps

490

AD-heavy deviation maps

492

DLBD deviation maps

494

FTD deviation maps

496

PSP deviation maps

498

MID deviation maps

500

MPH deviation maps

Claims (10)

A system, comprising: a storage device ( 14 ) with several routines stored therein; a processor ( 12 ) configured to execute the plurality of routines stored in the storage device, the plurality of routines comprising: a routine configured to, when executed, access ( 282 ) to a patient image deviation evaluation ( 250 ) that causes a difference between patient image data ( 242 ) and reference data representative of a population segment ( 244 ) indicates; a routine configured to execute an access when executed ( 284 ) to a patient non-image deviation score ( 270 ) that cause a difference between non-image data ( 262 ) of the patient and representative non-image data representative of the population segment; a routine configured to execute, when executed, a generation ( 286 ) of a report with a visual representation of a deviation of the patient image data from the reference image data, and a visual representation ( 296 ) causing patient non-image data deviations from reference non-image data; and a routine configured to execute, when executed, an output ( 288 ) of the report. The system of claim 1, wherein the plurality of routines include routines ( 248 . 268 ) for calculating the patient image deviation score and the patient non-image deviation score. System according to claim 1, which comprises at least one additional Storage device having a database stored therein being the database and for a plurality of population segments representative reference image data and reference non-image data, wherein the population segments based on at least one of age, race or gender are classified. Computer-implemented method, with the steps: accessing ( 282 ) to a picture deviation evaluation ( 250 ) of a patient ( 36 ) by comparing patient image data ( 242 ) with standardized image data representative of a population of persons ( 244 ) is derived; Access ( 284 ) to a non-image deviation assessment ( 250 ) of a patient obtained by comparing patient non-image data ( 242 ) with standardized non-image data representative of a population of persons ( 244 ) is derived; Processing the image deviation evaluation and the non-image deviation evaluation to obtain a visual result ( 296 ) to create ( 286 ) representing both a difference between the patient image data and the standardized image data and a difference between the patient non-image data and the standardized non-image data; and ads ( 288 ) of the visual result to make a diagnosis ( 290 ) of a medical condition of the patient. The method of claim 4, wherein the image deviation score at least one score based on a deviation of the patient image data from the standardized patient image data with respect to at least one of metabolic activity the brain of the patient, physical anatomy of the brain, or functional activity of the brain. The method of claim 4, wherein the population of persons is substantially a ge common property with persons sharing the patient, and wherein at least one of the standardized image data or the standardized non-image data is standardized on the basis of the substantially common property so that the variance score of the image or non-image being accessed is indicate a deviation of the patient image data or patient non-image data from the corresponding standardized image or non-image data representative of the persons sharing the substantially common characteristic with the patient. The method of claim 6, wherein the standardized Image data averaged image data for Include the persons who are the essentially common Share property. The method of claim 4, wherein the patient non-image data is clinical Include patient data. The method of claim 4, wherein the patient non-image data is patient data in terms of one or more of the following: patient history, Patient vital signs, functional tests, cognitive tests, neurological Tests or genetic tests. The method of claim 4, wherein the visual output is a Graphical representation involves the size of the difference between the Patient image data and patient non-image data and the corresponding standardized image data or non-image data.